Olivier Terzo

Olivier Terzo

Auto-generated profile, based on publicly available information

Olivier Terzo

LINKS foundation

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2024
Verified
Conference Paper
Open access
FLFrancesco Lubrano
Francesco Lubrano
CVChiara Vercellino
Chiara Vercellino
GVGiacomo Vitali
Giacomo Vitali
PVPaolo Viviani
Paolo Viviani
Alberto SciontiAlberto Scionti
Alberto Scionti
OTOlivier Terzo
Olivier Terzo
In High-Performance Computing (HPC), workflows are utilized to define and manage a set of interdependent computations which allow the users to extract insights from (scientific) numerical simulations or data analytics. HPC platforms can perform extreme-scale simulations, combining Artificial Intelligence (AI) training and inference and data analytics (we refer to heterogeneous workflows), by providing tools and computing resources which serve a variety of use-cases spanning very diverse application domains (e.g., weather forecasting, quantum mechanics, etc.). Executing such workflows at scale requires to handle dependencies, job submission automation, I/O mechanisms. Despite State-of-the-Art batch schedulers can be configured and integrated with tools accomplishing this automation, a number of cases where resource allocation can lead to inefficiencies still exist. In this paper, to overcome these limitations, we present the WARP (Workflow-aware Advanced Resource Planner), a tool that integrates with workflow management tools and batch schedulers, to reserve in advance resources for an optimal execution of jobs, based on their duration, dependencies and machine load. WARP has been designed to minimize the overall workflow execution, without violating the priority policies for cluster users imposed by the system administrators.

16 May 2012
Verified
Book Chapter
Open access
OTOlivier Terzo
Olivier Terzo
Pietro RuiuPietro Ruiu
Pietro Ruiu
LMLorenzo Mossucca
Lorenzo Mossucca
MAMatteo Alessandro
Matteo Alessandro
FVFrancesca Vipi
Francesca Vipi
The accurate and efficient solution of Maxwell's equation is the problem addressed by the scientific discipline called Computational ElectroMagnetics (CEM). Many macroscopic phenomena in a great number of fields are governed by this set of differential equations: electronic, geophysics, medical and biomedical technologies, virtual EM prototyping, besides the traditional antenna and propagation applications. Therefore, many efforts are focussed on the development of new and more efficient approach to solve Maxwell's equation. The interest in CEM applications is growing on. Several problems, hard to figure out few years ago, can now be easily addressed thanks to the reliability and flexibility of new technologies, together with the increased computational power. This technology evolution opens the possibility to address large and complex tasks. Many of these applications aim to simulate the electromagnetic behavior, for example in terms of input impedance and radiation pattern in antenna problems, or Radar Cross Section for scattering applications. Instead, problems, which solution requires high accuracy, need to implement full wave analysis techniques, e.g., virtual prototyping context, where the objective is to obtain reliable simulations in order to minimize measurement number, and as consequence their cost. Besides, other tasks require the analysis of complete structures (that include an high number of details) by directly simulating a CAD Model. This approach allows to relieve researcher of the burden of removing useless details, while maintaining the original complexity and taking into account all details. Unfortunately, this reduction implies: (a) high computational effort, due to the increased number of degrees of freedom, and (b) worsening of spectral properties of the linear system during complex analysis. The above considerations underline the needs to identify appropriate information technologies that ease solution achievement and fasten required elaborations. The authors analysis and expertise infer that Grid Computing techniques can be very useful to these purposes. Grids appear mainly in high performance computing environments. In this context, hundreds of off-the-shelf nodes are linked together and work in parallel to solve problems, that, previously, could be addressed sequentially or by using supercomputers. Grid Computing is a technique developed to elaborate enormous amounts of data and enables large-scale resource sharing to solve problem by exploiting distributed scenarios. The main advantage of Grid is due to parallel computing, indeed if a problem can be split in smaller tasks, that can be executed independently, its solution calculation fasten up considerably. To exploit this advantage, it is necessary to identify a technique able to split original electromagnetic task into a set of smaller subproblems. The Domain Decomposition (DD) technique, based on the block generation algorithm introduced in Matekovits et al. (2007) and Francavilla et al. (2011), perfectly addresses our requirements (see Section 3.4 for details). In this chapter, a Grid Computing infrastructure is presented. This architecture allows parallel block execution by distributing tasks to nodes that belong to the Grid. The set of nodes is composed by physical machines and virtualized ones. This feature enables great flexibility and increase available computational power. Furthermore, the presence of virtual nodes allows a full and efficient Grid usage, indeed the presented architecture can be used by different users that run different applications

21 June 2019
Verified
Book Chapter
Closed access
PDF file
SCsimone ciccia
simone ciccia
Alberto SciontiAlberto Scionti
Alberto Scionti
GGGiorgio Giordanengo
Giorgio Giordanengo
LPL. Pilosu
L. Pilosu
OTO. Terzo
O. Terzo

22 December 2016
Verified
Conference Paper
Closed access
Alberto SciontiAlberto Scionti
Alberto Scionti
Pietro RuiuPietro Ruiu
Pietro Ruiu
OTOlivier Terzo
Olivier Terzo
LSLuca SPOGLI
Luca SPOGLI
LALucilla Alfonsi
Lucilla Alfonsi
VRVincenzo Romano
Vincenzo Romano
There is a strong relationship between scientific research and technology advancement. The former generally focuses on studying phenomena happening in the real world, the latter improves tools that are at the basis of this research. From this perspective, information and communication technologies allow the implementation of ever faster tools for analyzing data generated by experiments. The aim of DemoGRAPE project is to study the interaction of the upper earth atmosphere and the GNSS (Global Navigation Satellite Systems) signals received at ground, in critical environments such as the polar regions. This paper describes the ICT infrastructure used to manage the software applications used to analyzed data collected during project experimental campaigns, taking into account the following constraints: (i) the intellectual property of the applications must be protected, (ii) the underlying infrastructure resembles a cloud-federation, (iii) data are over-sized, (iv) provide a unified vision of the available resources to the user (i.e., what are the available applications, and where experimental data reside). Leveraging on a lightweight virtualization system, we proposed a management system that copes with all these four constraints. A case study is used to show the process of deploying an application through the proposed system on a specific node where data of interest reside.

17 September 2023
Verified
Book Chapter
Closed access
PDF file
PVPaolo Viviani
Paolo Viviani
IGIlaria Gesmundo
Ilaria Gesmundo
EGElios Ghinato
Elios Ghinato
AAAndres Agudelo-Toro
Andres Agudelo-Toro
CVChiara Vercellino
Chiara Vercellino
HSHansjörg Scherberger
Hansjörg Scherberger

24 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
FVFabio Vitale
Fabio Vitale
FCFrancesca Cibrario
Francesca Cibrario
DVDavide Veronelli
Davide Veronelli
CVChiara Vercellino
Chiara Vercellino
VZValeria Zaffaroni
Valeria Zaffaroni
MBMarco Bianchetti
Marco Bianchetti
Financial portfolio optimization is often framed through mean–variance objectives, yet real profit-and-loss (P&L) scenario distributions are typically discrete and non-Gaussian. To explore realistic P&L distributions, we propose an objective function based on exponential tilting and certainty equivalent under constant absolute risk aversion. We then derive a second-order approximation, recovering a quadratic optimization problem solvable through mixed integer quadratic programming (MIQP) and quadratic unconstrained binary optimization (QUBO). Constraints in the QUBO formulation are incorporated via Lagrangian relaxation and slack variable approaches, enabling a direct comparison between classical constrained MIQP and quantum-inspired methods. In order to study how exponential tilting affects mean, standard deviation, and tail-risk measures such as Value at Risk and Conditional Value at Risk, we design an experimental protocol based on scanning a grid of tilt parameters and solving the associated optimization problems. The results on a realistic trading portfolio show how the tilts can be tuned to optimize different risk-return profiles while remaining competitive with those found using other state-ofthe-art approaches. Moreover, performance analysis suggests that, even using classical solvers, the QUBO formulation with Lagrangian relaxation scales better than the MIQP approach, providing the best constraint encoding strategy.